S^2tory: Story Spine Distillation for Movie Script Summarization

• URL: http://arxiv.org/abs/2605.03244v1
• Date: Tue, 05 May 2026 00:25:09 GMT
• Title: S^2tory: Story Spine Distillation for Movie Script Summarization
• Abstract summary: Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure.<n>We introduce S2tory, a framework that leverages character development trajectories to identify plot nuclei.<n>Experiments on the MovieSum dataset demonstrate state-of-the-art semantic fidelity at approximately 3.5x compression, and zero-shot evaluation on BookSum confirms strong out-of-domain generalization.
• Score: 12.310927788766854
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure, which makes surface-level saliency methods ineffective at preserving core story progression. To address this, we introduce S^2tory (Story Spine Distillation), a narratology-grounded framework that leverages character development trajectories to identify plot nuclei, the essential events that drive the narrative forward, while filtering out peripheral satellite events that merely enrich atmosphere or emotion. Our Narrative Expert Agent (NEAgent) performs theory-constrained reasoning, whose distilled knowledge conditions a small model to identify plot nuclei. Another model then uses these plot nuclei to generate the summary. Experiments on the MovieSum dataset demonstrate state-of-the-art semantic fidelity at approximately 3.5x compression, and zero-shot evaluation on BookSum confirms strong out-of-domain generalization. Human evaluation further validates that narratological theory provides an indispensable foundation for modeling complex, non-linear narratives.

Related papers

• MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing [14.61147082072489]
  We formulate Vibe Narrativizing as the task of turning natural-language writing requirements into a finished story.<n>We present MUSE, a Theory-Harnessed Story Engine.<n>MUSE derives reusable guidance from Robert McKee's story theory through rule atomization, semantic consolidation, and mechanism abstraction.
  arXiv  Detail & Related papers  (2026-09-14T08:09:44Z)
• Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books [52.08691427871138]
  We propose a training framework that decouples reasoning from generation.<n>Our approach consists of a reasoning model that produces a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description.
  arXiv  Detail & Related papers  (2026-04-13T13:19:56Z)
• NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control [59.6128550986024]
  NarraScore is a hierarchical framework predicated on the core insight that emotion serves as a high-density compression of narrative logic.<n>NarraScore employs a Dual-Branch Injection strategy to reconcile global structure with local dynamism.<n>NarraScore achieves state-of-the-art consistency and narrative alignment with negligible computational overhead.
  arXiv  Detail & Related papers  (2026-02-09T09:39:42Z)
• Generating Visual Stories with Grounded and Coreferent Characters [63.07511918366848]
  We present the first model capable of predicting visual stories with consistently grounded and coreferent character mentions.<n>Our model is finetuned on a new dataset which we build on top of the widely used VIST benchmark.<n>We also propose new evaluation metrics to measure the richness of characters and coreference in stories.
  arXiv  Detail & Related papers  (2024-09-20T14:56:33Z)
• NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization [26.80378373420446]
  NarraSum is a large-scale narrative summarization dataset. It contains 122K narrative documents, which are collected from plot descriptions of movies and TV episodes with diverse genres, and their corresponding abstractive summaries. Experiments show that there is a large performance gap between humans and the state-of-the-art summarization models on NarraSum.
  arXiv  Detail & Related papers  (2022-12-02T22:51:51Z)
• SummScreen: A Dataset for Abstractive Screenplay Summarization [52.56760815805357]
  SummScreen is a dataset comprised of pairs of TV series transcripts and human written recaps. Plot details are often expressed indirectly in character dialogues and may be scattered across the entirety of the transcript. Since characters are fundamental to TV series, we also propose two entity-centric evaluation metrics.
  arXiv  Detail & Related papers  (2021-04-14T19:37:40Z)
• PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking [128.76063992147016]
  We present PlotMachines, a neural narrative model that learns to transform an outline into a coherent story by tracking the dynamic plot states. In addition, we enrich PlotMachines with high-level discourse structure so that the model can learn different writing styles corresponding to different parts of the narrative.
  arXiv  Detail & Related papers  (2020-04-30T17:16:31Z)
• Screenplay Summarization Using Latent Narrative Structure [78.45316339164133]
  We propose to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models. We formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays. Experimental results on the CSI corpus of TV screenplays, which we augment with scene-level summarization labels, show that latent turning points correlate with important aspects of a CSI episode.
  arXiv  Detail & Related papers  (2020-04-27T11:54:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.